Mapping Landslides with VHR Satellite Imagery

Copernicus Emergency Management Service is using Very High Resolution (VHR) satellite imagery supplied by European Space Imaging to create grading maps and analyse damage after landslides in Germany.

A former mining region in Saxony, Germany, has experienced numerous landslides since September 2018. After two major incidents in March and April 2019, European Space Imaging was activated by the Copernicus EMS to supply Very High Resolution optical satellite imagery at 50 cm collected by WorldView-2 & -3 in order to assess possible effects on drinking water infrastructure in the area.

The VHR imagery was used by the Copernicus EMS service provider, SERTIT, to create a grading map used to evaluate the scope and intensity of damages in Saxony, Germany. Information within the map indicates that the landslides have blocked a tunnel connecting two water reservoirs, potentially having severe impact on drinking water in the Berlin area.

Before-afterBefore-after-2

Before and after landslide | Saxony, Germany | Captured by WorldView-2 & 3 on 29 August 2018 and 8 April 2019 respectively | © European Space Imaging

European Space Imaging is a provider of Very High Resolution optical satellite imagery for the Copernicus EMS due to the company’s ability to directly task the WorldView satellite constellation from its’ ground station at the German Aerospace Centre (DLR) near Munich. They are able to rapidly deliver both archived and newly collected data orders for European agencies and institutions as well as commercial users. In this case, European Space Imaging delivered the archived imagery in only 50 minutes, allowing Copernicus EMS to have the maps available to the Joint Information and Situation Centre of the Federal Government and the Federal States (GMLZ) only hours later.

In emergency situations, VHR satellite imagery is a crucial component for both damage assessment and relief planning. It’s imperative that data can be collected and delivered as fast as possible. For this reason, European Space Imaging is available 24/7 for emergency orders.

To learn more about the landslides and view the grading map, visit the Copernicus EMS website.

Share on facebook
Share on twitter
Share on linkedin

Related Stories

Scroll to Top

Architecture of ResNet34-UNet model

UNet architecture for semantic segmentation with ResNet34 as encoder or feature extraction part. ResNet34 is used as an encoder or feature extractor in the contracting path and the corresponding symmetric expanding path predicts the dense segmentation output.

Architecture of VGG16-UNet model

UNet architecture for semantic segmentation with VGG16 as the encoder or feature extractor. VGG16 is used as an encoder or feature extractor in the contracting path and the corresponding symmetric expanding path predicts the dense segmentation output.

Architecture of ResNet34-FCN model

In this model, ResNet34 is used for feature extraction and the FCN operation remains as is. The feature of ResNet architecture is exploited where just like VGG, as the number of filters double, the feature map size gets halved. This gives a similarity to VGG and ResNet architecture while supporting deeper architecture and addressing the issue of vanishing gradients while also being faster. The fully connected layer at the output of ResNet34 is not used and instead converted to fully convolutional layer by means of 1×1 convolution.

Architecture of VGG16-FCN model

In this model, VGG16 is used for feature extraction which also performs the function of an encoder. The fully connected layer of the VGG16 is not used and instead converted to fully convolutional layer by means of 1×1 convolution.

X